{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/point-transformer-1","title":"Point Transformer","arxiv_id":"2012.09164","date":"2020-12-16","proceeding":"ICCV 2021 10","authors":["Hengshuang Zhao","Li Jiang","Jiaya Jia","Philip Torr","Vladlen Koltun"],"abstract":"Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection. Inspired by this success, we investigate the application of self-attention networks to 3D point cloud processing. We design self-attention layers for point clouds and use these to construct self-attention networks for tasks such as semantic scene segmentation, object part segmentation, and object classification. Our Point Transformer design improves upon prior work across domains and tasks. For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70.4% on Area 5, outperforming the strongest prior model by 3.3 absolute percentage points and crossing the 70% mIoU threshold for the first time.","url_abs":"https://arxiv.org/abs/2012.09164v2","url_pdf":"https://arxiv.org/pdf/2012.09164v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"point-transformer-1","repo_url":"https://github.com/Pointcept/Pointcept","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/2023-MindSpore-1/ms-code-48","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/KernelA/pytorch-point-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/Meowuu7/Point-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/POSTECH-CVLab/FastPointTransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/POSTECH-CVLab/point-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/Sharpiless/Point-Transformer-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/alzmzyy/pointtransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/lucidrains/point-transformer-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/qq456cvb/Point-Transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/rauleun/point-transformer-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/tkdguraa/point-transformer-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://gitee.com/gai-shaoyan/mind3d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/pointtransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/MS-Mind/MS-Code-06/tree/main/pointtransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/Mind23-2/MindCode-5/tree/main/pointtransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/pointtransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/code-implementation1/Code6/tree/main/pointtransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/engelnico/point-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/gofinge/pointtransformerv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/isl-org/Open3D-ML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/jxl152/Point-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/lifebeyondexpectations/eccv22-pointmixer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"point-transformer-1","repo_url":"https://github.com/sh4175515/PointTransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"point-cloud-segmentation","task_name":"Point Cloud Segmentation"},{"task_slug":"scene-segmentation","task_name":"Scene Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"PointTransformer","rank_in_archive_order":19,"of":67,"metrics":{"Class Average IoU":"83.7","Instance Average IoU":"86.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"PointTransformer","rank_in_archive_order":50,"of":111,"metrics":{"Mean Accuracy":"90.6","Overall Accuracy":"93.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-s3dis","task":"3D Semantic Segmentation","dataset":"S3DIS","model":"PointTransformer","rank_in_archive_order":4,"of":6,"metrics":{"mIoU (6-Fold)":"73.5","mIoU (Area-5)":"70.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-stpls3d","task":"3D Semantic Segmentation","dataset":"STPLS3D","model":"Point transformer","rank_in_archive_order":5,"of":6,"metrics":{"mIOU":"47.64"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-segmentation-on-pointcloud-c","task":"Point Cloud Segmentation","dataset":"PointCloud-C","model":"PointTransformers","rank_in_archive_order":7,"of":11,"metrics":{"mean Corruption Error (mCE)":"1.049"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"PointTransformer","rank_in_archive_order":17,"of":54,"metrics":{"Mean IoU":"73.5","Number of params":"7.8M","Params (M)":"7.8","mAcc":"81.9","oAcc":"90.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"KPConv","rank_in_archive_order":24,"of":54,"metrics":{"Mean IoU":"70.6","Number of params":"14.1M","Params (M)":"14.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"PointCNN","rank_in_archive_order":36,"of":54,"metrics":{"Mean IoU":"65.4","Number of params":"N/A"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"SPGraph","rank_in_archive_order":42,"of":54,"metrics":{"Mean IoU":"62.1","Number of params":"N/A"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis","task":"Semantic Segmentation","dataset":"S3DIS","model":"PointNet","rank_in_archive_order":51,"of":54,"metrics":{"Mean IoU":"47.6","Number of params":"N/A"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"PointTransformer","rank_in_archive_order":32,"of":61,"metrics":{"Number of params":"7.8M","mAcc":"76.5","mIoU":"70.4","oAcc":"90.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"PointCNN","rank_in_archive_order":53,"of":61,"metrics":{"Number of params":"N/A","mIoU":"57.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-s3dis-area5","task":"Semantic Segmentation","dataset":"S3DIS Area5","model":"PointNet","rank_in_archive_order":56,"of":61,"metrics":{"Number of params":"N/A","mIoU":"41.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.09164","atlas_url":"https://app.syntology.ai/?focus=2012.09164","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2012.09164"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.09164\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.09164"},"call":"get_concepts_for_paper(arxiv_id=\"2012.09164\")"}],"by_repo":[{"repo":"Pointcept/Pointcept","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2503.16429"],"harvested_for_calls":[{"arxiv_id":"2503.16429","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.16429"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.16429\")"}]},{"repo":"2023-MindSpore-1/ms-code-48","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"KernelA/pytorch-point-transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Meowuu7/Point-Transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"POSTECH-CVLab/FastPointTransformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2112.04702"],"harvested_for_calls":[{"arxiv_id":"2112.04702","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.04702"},"call":"get_harvested_code_for_paper(arxiv_id=\"2112.04702\")"}]},{"repo":"POSTECH-CVLab/point-transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Sharpiless/Point-Transformer-Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"alzmzyy/pointtransformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lucidrains/point-transformer-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"qq456cvb/Point-Transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2012.09688"],"harvested_for_calls":[{"arxiv_id":"2012.09688","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2012.09688"},"call":"get_harvested_code_for_paper(arxiv_id=\"2012.09688\")"}]},{"repo":"rauleun/point-transformer-tf2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tkdguraa/point-transformer-tensorflow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"gitee.com/gai-shaoyan/mind3d","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-215","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MS-Mind/MS-Code-06","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Mind23-2/MindCode-5","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-paper-code-2/code2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"code-implementation1/Code6","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"engelnico/point-transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2011.00931"],"harvested_for_calls":[{"arxiv_id":"2011.00931","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2011.00931"},"call":"get_harvested_code_for_paper(arxiv_id=\"2011.00931\")"}]},{"repo":"gofinge/pointtransformerv2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"isl-org/Open3D-ML","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":5,"harvested_for":["1706.01307","1812.04244","1812.05784","1904.08889","1907.03739"],"harvested_for_calls":[{"arxiv_id":"1706.01307","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.01307"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.01307\")"},{"arxiv_id":"1812.04244","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.04244"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.04244\")"},{"arxiv_id":"1812.05784","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.05784"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.05784\")"},{"arxiv_id":"1904.08889","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.08889"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.08889\")"},{"arxiv_id":"1907.03739","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1907.03739"},"call":"get_harvested_code_for_paper(arxiv_id=\"1907.03739\")"}]},{"repo":"jxl152/Point-Transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lifebeyondexpectations/eccv22-pointmixer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sh4175515/PointTransformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1347ca73227e924c2274ccb248e2660a63d8ad5166e33fb8cc7f093c227dd871","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}